2018/7/8 pandas学习笔记 数据加载、存储

读写文本格式的数据

In [3]: import pandas as pd

In [4]: df = pd.read_csv('ex1.csv')   read_csv函数可以把源文件里的逗号去掉

In [5]: df
Out[5]:
   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

In [6]: pd.read_table('ex1.csv', sep=',')   read_table需要加上sep指定逗号隔开
Out[6]:
   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

In [13]: pd.read_csv('ex2.csv',header=None)  列名为空 
Out[13]:
   0   1   2   3      4
0  1   2   3   4  hello
1  5   6   7   8  world
2  9  10  11  12    foo

In [14]: pd.read_csv('ex2.csv',names=['a','b','c','d','message'])   添加列名
Out[14]:
   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

In [15]: pd.read_csv('ex2.csv',names=['a','b','c','d','message'],index_col='message')  将某一列作为索引
Out[15]:
         a   b   c   d
message
hello    1   2   3   4
world    5   6   7   8
foo      9  10  11  12

In [16]: pd.read_csv('csv_mindex.csv')  
Out[16]:
  key1 key2  value1  value2
0  one    a       1       2
1  one    b       3       4
2  one    c       5       6
3  one    d       7       8
4  two    a       9      10
5  two    b      11      12
6  two    c      13      14
7  two    d      15      16

In [17]: pd.read_csv('csv_mindex.csv',index_col=['key1','key2'])  层次化索引
Out[17]:
           value1  value2
key1 key2
one  a          1       2
     b          3       4
     c          5       6
     d          7       8
two  a          9      10
     b         11      12
     c         13      14
     d         15      16

In [18]: list(open('ex3.txt'))
Out[18]:
['            A         B         C\n',
 'aaa -0.264438 -1.026059 -0.619500\n',
 'bbb  0.927272  0.302904 -0.032399\n',
 'ccc -0.264273 -0.386314 -0.217601\n',
 'ddd -0.871858 -0.348382  1.100491\n']

In [19]: pd.read_table('ex3.txt', sep='\s+')  分隔符不固定时，可以用正则表达式'\s+'
Out[19]:
            A         B         C
aaa -0.264438 -1.026059 -0.619500
bbb  0.927272  0.302904 -0.032399
ccc -0.264273 -0.386314 -0.217601
ddd -0.871858 -0.348382  1.100491

In [26]: pd.read_csv('ex4.csv',skiprows=[0,2,3])   skipros可以跳过指定行
Out[26]:
   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

In [27]: result = pd.read_csv('ex5.csv')  可以自动检测常见的空，如NULL Nan

In [28]: result
Out[28]:
  something  a   b     c   d message
0       one  1   2   3.0   4     NaN
1       two  5   6   NaN   8   world
2     three  9  10  11.0  12     foo

In [29]: pd.isnull(result)
Out[29]:
   something      a      b      c      d  message
0      False  False  False  False  False     True
1      False  False  False   True  False    False
2      False  False  False  False  False    False

In [30]: sentinels = {'message': ['foo','NA'], 'something': [ 'two']}

In [31]: pd.read_csv('ex5.csv', na_values = sentinels)   na_values可以将指定字符转换为nan
Out[31]:
  something  a   b     c   d message
0       one  1   2   3.0   4     NaN
1       NaN  5   6   NaN   8   world
2     three  9  10  11.0  12     NaN